Update README.md

README.md

@@ -17,20 +17,20 @@ This checkpoint is trained with: https://github.com/hiyouga/LLaMA-Efficient-Tuni
 Usage:
 
 ```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
 from peft import PeftModel
 
+
 tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/baichuan-7B", trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained("baichuan-inc/baichuan-7B", device_map="auto", trust_remote_code=True)
 model = PeftModel.from_pretrained(model, "hiyouga/baichuan-7b-sft")
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 
 query = "晚上睡不着怎么办"
 
 inputs = tokenizer(["<human>:{}\n<bot>:".format(query)], return_tensors="pt")
 inputs = inputs.to("cuda")
-generate_ids = model.generate(**inputs)
-output = tokenizer.batch_decode(generate_ids)[0]
-print(output)
+generate_ids = model.generate(**inputs, max_new_tokens=256, streamer=streamer)
 ```
 
 You could also alternatively launch a CLI demo by using the script in https://github.com/hiyouga/LLaMA-Efficient-Tuning